arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.18364cs.LGmath.OC
收藏

近端盆地跳跃:有保证的全局优化

Proximal basin hopping: global optimization with guarantees

LJAD;MALGA;Université Côte d’Azur(法国尼斯大学);Università di Genova(热那亚大学);CNRS(国家科学研究中心)

Guillaume Lauga, Cesare Molinari, Samuel Vaiter

AI总结:

提出近端盆地跳跃(PBH)理论框架,结合近端优化与局部最小化,构建算法以高概率收敛到全局最小值,在合成硬函数和深度学习标度律拟合等实际问题中表现优于有理论保证的已知算法,且维度越高性能差距越大。

摘要:

全局优化是一个具有挑战性的问题,大量算法展示了经验上的成功,但缺乏理论支持。在这项工作中,我们提出了一个名为近端盆地跳跃(PBH)的新理论框架,精心设计以结合近端优化和局部最小化。我们利用它构建了一个实用算法,在使用有限样本时以高概率收敛到全局最小值。近端盆地跳跃在标准合成硬函数和实际问题(如拟合深度学习标度律)上优于具有理论保证的已知算法。此外,维度越高,性能差距越大。

英文摘要:

Global optimization is a challenging problem, with plenty of algorithms displaying empirical success, but scarce theoretical backing. In this work, we propose a new theoretical framework called Proximal Basin Hopping (PBH), carefully tailored to combine proximal optimization and local minimization. We use it to construct a practical algorithm that converges to the global minimizer with high probability, when using a finite amount of samples. Proximal Basin Hopping outperforms well known algorithms with theoretical backing on standard synthetic hard functions, and real problems such as fitting scaling laws for deep learning. Furthermore, the higher the dimension, the better the performance gap.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑